Bandit PCA

Bandit PCA Abstract:

We consider a partial-feedback variant of the well-studied online PCA problem where a learner attempts to predict a sequence of d-dimensional vectors in terms of a quadratic loss, while only having limited feedback about the environment's choices. We focus on a natural notion of bandit feedback where the learner only observes the loss associated with its own prediction. Based on the classical observation that this decision-making problem can be lifted to the space of density matrices, we propose an algorithm that is shown to achieve a regret of O(d^3/2√T) after T rounds in the worst case. We also prove data-dependent bounds that improve on the basic result when the loss matrices of the environment have bounded rank or the loss of the best action is bounded. One version of our algorithm runs in O(d) time per trial which massively improves over every previously known online PCA method. We complement these results by a lower bound of Ω(d√T).